Skip to content

Emory-AIMS/direct_token_optimization

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Direct Token Optimization (DTO)

Overview

This repository provides implementation and some experimental results of Direct Token Optimization. The repository suppports unlearning TOFU dataset and MUSE-HP dataset. To evaluate, please refer to MUSE Benchmark and open-unlearning.

Configurations

Configuration files are located in the configs/ directory and can be customized for different experiments.

Data

  • Tofu dataset is available in Huggingface.
  • For MUSE harry potter dataset, download the harry potter dataset from MUSE-Benchmark

Requirements

The project requires Python 3.10+ with dependencies listed in requirements.txt, including PyTorch, Transformers, Hydra, and other ML libraries.

Usage

We provide an example script to run. Please refer to run_forget01.sh.

Results

Under the results folder, we provide an evaluation result from TOFU benchmark.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Python 99.8%
  • Shell 0.2%